The rapid evolution of digital currency trading, fueled by the integration of blockchain technology, has led to both innovation and the emergence of smart Ponzi schemes. A smart Ponzi scheme is a fraudulent investment operation in smart contract that uses funds from new investors to pay returns to earlier investors. Traditional Ponzi scheme detection methods based on deep learning typically rely on fully supervised models, which require large amounts of labeled data. However, such data is often scarce, hindering effective model training. To address this challenge, we propose a novel contrastive learning framework, CASPER (Contrastive Approach for Smart Ponzi detectER with more negative samples), designed to enhance smart Ponzi scheme detection in blockchain transactions. By leveraging contrastive learning techniques, CASPER can learn more effective representations of smart contract source code using unlabeled datasets, significantly reducing both operational costs and system complexity. We evaluate CASPER on the XBlock dataset, where it outperforms the baseline by 2.3% in F1 score when trained with 100% labeled data. More impressively, with only 25% labeled data, CASPER achieves an F1 score nearly 20% higher than the baseline under identical experimental conditions. These results highlight CASPER's potential for effective and cost-efficient detection of smart Ponzi schemes, paving the way for scalable fraud detection solutions in the future.

Temporal knowledge graph (TKG) extrapolation aims to predict future, previously unseen events based on historical facts. However, most existing temporal knowledge graph extrapolation methods either focus on global cyclic regularities or on local adjacent transitions. These methods overlook the multi-granularity nature of temporal signals and often rely on heuristic fusion schemes that are sensitive to noise. To address these limitations, we propose MTRM, a Multi-granularity Trend Retrieval and Modeling framework for TKG extrapolation. Specifically, we first apply semantic clustering to retrieve a compact set of long-term trend clusters from sequences of historical subgraphs, capturing enduring interaction patterns. Then, we introduce a trend-aware attention-enhancing evolution module with an auxiliary contrastive loss to learn fine-grained short-term dynamics by aligning each hidden state with its subsequent subgraph. To integrate information at different granularities, we design a multi-granularity attention layer that adaptively fuses the long-term clusters with the short-term trend states for each query entity. Additionally, an inter-granularity contrastive objective is employed to align these representations and enhance robustness to noisy snapshots. Experiments on four benchmark datasets demonstrate that MTRM outperforms state-of-the-art baselines by up to 5.89% in mean reciprocal rank (MRR), indicating improved robustness on large-scale noisy event streams. Moreover, MTRM provides interpretable insights into how long- and short-term temporal granularities jointly drive future-event prediction.

Fusing side information in session-based recommendation is crucial for improving the performance of next-item prediction by providing additional context. Recent methods optimize attention weights by combining item and side information embeddings. However, semantic heterogeneity between item IDs and side information introduces computational noise in attention calculation, leading to inconsistencies in user interest modeling and reducing the accuracy of candidate item scores. These methods also often fail to leverage session-based re-interaction patterns, limiting improvements in score prediction during the decoding phase. To address these challenges, we propose ScoreNet, a consistency-driven framework with multi-side information fusion for session-based recommendation. ScoreNet explicitly models users' persistent preferences, generating consistent decoding scores for candidate items within a unified framework. It incorporates a multi-path re-engagement network to capture re-interaction behavior patterns in a semantic-agnostic manner, enhancing side information fusion while avoiding semantic interference. Additionally, a position-enhanced consistent scoring network redistributes attention scores within sessions, improving prediction accuracy, especially for items with limited interactions. Extensive experiments on three real-world datasets demonstrate that ScoreNet outperforms state-of-the-art models.

Current rumor detectors exhibit limitations in fully exploiting responses to the source tweet as essential public opinions, and in explaining and indicating the reliability of the results obtained. Additionally, the joint utilization of both responses and the multimodal source content for detection presents challenges due to the heterogeneous nature of the data points. In this work, to address the first challenge, we initially prompt the Large Language Model (LLM) with both multimodal source content and the corresponding response set to extract contrasting evidence to enable maximal utilization of informative responses. To overcome the second challenge, we introduce an uncertainty-aware evidential evaluator to assess the evidence intensity from the multimodal source content and dual-sided reasoning, from which the final prediction is derived. As we model the second-order probability, we can effectively indicate the model’s uncertainty (i.e., the reliability) of the results. The reasoning from the correct perspective also serves as a natural language-based explanation. To this end, the third challenge is also addressed as we fully leverage the available resources. Extensive experiments validate the effectiveness, uncertainty awareness in predictions, helpful explainability for human judgment, and superior efficiency of our approach compared to contemporary works utilizing LLMs.

Blockchain technology has catalyzed innovation in digital currency trading but has also facilitated the emergence of smart Ponzi schemes, wherein returns to earlier investors are fraudulently paid using capital from newer participants. Deep learning-based detection methods show promise in identifying these schemes. However, they rely heavily on large amounts of labeled data, which are often limited in real-world applications. This paper introduces Semi-Supervised Smart Ponzi Identification (S3PI), a novel framework designed to address data scarcity by integrating contrastive learning for robust contract representation. The proposed semi-supervised approach reduces reliance on extensive labels, thereby lowering operational complexity and cost, while maintaining high detection accuracy. Experiments on the XBlock dataset indicate that S3PI achieves strong performance with only 25% labeled data, surpassing the best baseline by approximately 10%. Further experiments on multiple datasets evaluate the model’s transferability and generalization across different datasets, demonstrating its adaptability to diverse data distributions and effectiveness in varied settings. This result highlights its effectiveness in detecting Ponzi schemes under label-scarce conditions, demonstrating the potential of semi-supervised learning in smart contract fraud detection. These findings suggest that S3PI offers a scalable and efficient solution for fraud detection in blockchain systems.

Speech enhancement aims to recover clean speech from complex noise backgrounds. This paper proposes a novel information processing module dubbed dynamic scene perception module (DSPM) that can help existing systems to accommodate various complex scenarios. The inspiration of DSPM is based on the observation that different regions of the noisy spectrum in different scenarios have different enhancing requirements. Concretely, DSPM consists of two parts, one for dynamic scene estimation, and the other for adaptive region perception. In particular, the scene estimator utilizes a spectrum-energy-based attention mechanism to obtain the coefficients of each convolution kernel. Then, at each position’ the region perceptron chooses the corresponding kernels by considering the requirements of the current region (preserve vocals or suppress noise). Systematic evaluations on the TIMIT corpus and Voice Bank + DEMAND demonstrate the effectiveness of our method. Compared with the existing systems, our proposed method achieved better performance under various SNR conditions and complex noise scenarios.

Speech enhancement aims to restore clean speech from noisy environments. In recent years, skip connections have shown great promise in improving speech enhancement performance. Although directly transmitting low-level information is helpful for reconstructing the spectrum, the noise components negatively impact denoising results. In this letter, we propose IDANet, an end-to-end framework that incorporates an information distillation and aggregation unit to store fine-grained features and filter out noisy components through continuous distillation and recalibration. In addition, we design a novel decoding block equipped with deformable convolution and dynamic attention mechanism to further improve the capability of the reconstruction unit. Experimental results conducted on TIMIT corpus demonstrate that the proposed IDANet is efficient yet effective, e.g., the parameters of our model against the state-of-the-art model are 0.68M vs. 1.23M, and the performance boost on STOI and PESQ is 0.81% and 3.73%.

The redundant convolutional encoder-decoder network has proven useful in speech enhancement tasks. It can capture localized time-frequency details of speech signals through both the fully convolutional network structure and feature selection capability resulting from the encoder-decoder mechanism. However, it does not explicitly consider the signal filtering mechanism, which we regard as important for speech enhancement models. In this study, we introduce an attention mechanism into the convolutional encoderdecoder model. This mechanism adaptively filters channelwise feature responses by explicitly modeling attentions (on speech versus noise signals) between channels. Experimental results show that the proposed attention model is effective in capturing speech signals from background noise, and performs especially better in unseen noise conditions compared to other state-of-the-art models.

The identification of discriminative features of the Alzheimer's disease contributes to the diagnostic accuracy. Recently, the combination of different types of features has been actively used in the area of the AD classification. In this paper, we proposed a novel classification framework to jointly select features, which are extracted from the VBM analysis and texture analysis to distinguish between the AD and the NC. Furthermore, in order to capture robust discriminative features, we improve the feature subset selection by combining the SVM-RFE and covariance to take into account the relationship among features. In order to evaluate the proposed method, we have performed evaluations on the MRI acquiring from the ADNI database. Our experimental results showed the feature combination has better performance than the either morphometric features and texture features. Also, we demonstrated our method is better than the one without feature selection, PCA or others.